Edit ‘the_seventy_maxims_of_maximally_effective_machine_learning_engineers’

the_seventy_maxims_of_maximally_effective_machine_learning_engineers.myco

@@ -14,7 +14,7 @@ Based on [[https://schlockmercenary.fandom.com/wiki/The_Seventy_Maxims_of_Maxima
 *. A gentle learning rate turneth away divergence. Once the loss stabilizes, crank it up.
 *. Do unto others’ hyperparameters as you would have them do unto yours.
 *. “Innovative architecture” means never asking “did we implement a proper baseline?”
-*. Only you can prevent vanishing gradients.
+*. Only you can prevent reward hacking.
 *. Your model is in the leaderboards: be sure it has dropout.
 *. The longer training goes without overfitting, the bigger the validation-set disaster.
 *. If the optimizer is leading from the front, watch for exploding gradients in the rear.